How to run object detection on an ESP-EYE using Edge Impulse.
Plug your ESP-EYE into your PC's USB port then type in this:
# Clone repo, enter, and run
git clone https://github.com/JimothyJohn/uEye && cd uEye && ./Quickstart.sh
This code has only been tested on the ESP-EYE module.
-
Create your model using Edge Impulse.
-
Due to the board limitations you will need to train your model with 96x96 images and use the MobileNetV1 0.01:*
-
Download the Arduino library under the
Deployment
tab in the Edge Impulse studio
-
Save the .zip library you downloaded to lib/
-
Add library location to platformio.ini if needed
lib_deps = lib/<your-project>.zip
-
-
Compile and deploy the code to your board
pio run -t upload && pio device monitor
- TinyML ESP32-CAM: Edge Image classification with Edge Impulse
- https://github.com/v12345vtm/esp32-cam-webserver-arduino-simplified-arduino-html
- ESP32-CAM
- ESP-EYE
- Establish separate endpoints for image, predictions, and metrics
- Convert to async webserver
- Add telemetry for location via 6-axis transformations